Single Image Defogging Method Using Variational Approach for Edge-Preserving Regularization

Authors: Wan-Hyun Cho, In-Seop Na, Seong-ChaeSeo, Sang-Kyoon Kim, Soon-Young Park

Abstract:

In this paper, we propose the variational approach to solve single image defogging problem. In the inference process of the atmospheric veil, we defined new functional for atmospheric veil that satisfy edge-preserving regularization property. By using the fundamental lemma of calculus of variations, we derive the Euler-Lagrange equation foratmospheric veil that can find the maxima of a given functional. This equation can be solved by using a gradient decent method and time parameter. Then, we can have obtained the estimated atmospheric veil, and then have conducted the image restoration by using inferred atmospheric veil. Finally we have improved the contrast of restoration image by various histogram equalization methods. The experimental results show that the proposed method achieves rather good defogging results.

Keywords: Image defogging, Image restoration, Atmospheric veil, Transmission, Variational approach, Euler-Lagrange equation, Image enhancement.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1076846

References:

[1] R. Tan, “Visibility in bad weather from a single image,”inProc CVPR, 2008, pp. 1-8.
[2] R. Fattal,“Single image dehazing,” ACM Trans. Graphics, 27(3), 2008, pp.1-9.
[3] K. He., J. Sun and X. Tang,“Single image haze removal using dark,” channel prior, in Proc. CVPR, 2009. pp.1956-1963.
[4] J.-P. Tarel and N. Hautiere,“Fast visibility restoration from a single color or gray level image,” in Proc. ICCV, 2009, pp.2201-2208.
[5] A. K. Tripathi and S. Mukhopadhyay,“Single image fog removal using anisotropic diffusion,” IET Image Processing, 6(7), 2012, pp.966-975.
[6] S. Teboul, L. Blanc-Feraud, G. Aubert, and M. Barlaud, “Variational Approach for Edge-Preserving Regularization Using Coupled PDE’s,” IEEE Tran. On Image Processing, 7(3), 1998. pp.387-397.
[7] T. F. Chan, and L. A. Vese, “Active Contours Without Edges,” IEEE Tran. On Image Precessing, 10(2), 2001, pp.266-277.
[8] L. I. Rudin,S. Osher and E. Fatemi, “Nonlinear total variation based noise removal algorithms,”Physica, D, 60, 1992, pp.259-268.
[9] Calculus of variations, Wikipedia, the free encyclopedia.
[10] Euler-Lagrange equation, Wikipedia, the free encyclopedia.